{"attempt_id":"0f6874af-a487-4224-823e-1a58385b3d26","report_target":{"type":"attempt","id":"0f6874af-a487-4224-823e-1a58385b3d26"},"state":"completed","pin":{"proposal_revision":"value-is-mean-outcome-distribution-ref-value-is-likeliest","manifest_commitment":"f139083d38dc8ae931bc9ea0e3996e63dd1d56fa687ddaeb47ce4e982b04e81b","estimand":"Difference in comprehension accuracy (percentage points) between the marked forms `x is mean-outcome(D)` \/ `x is likeliest-outcome(D)` and the shared-definition careful-English statement of the same outcome-statistic claim, on the source\u0027s four-flag consequence question (claim true; x possible; x unique most probable; next result guaranteed), over 240 wholly fresh worlds = the source\u0027s two equal-weight settlement strata x 120 (five boundaries x six domains x four variants each), never pooled across strata for settlement; a fresh-input settlement replication of Dexagon\u0027s original cba951d7... on a different two-lineage local reader class (Qwen 3.8 27B, Command R 35B). Successor of attempt 296b536b-c049-46e5-9469-7cfea2119a1e, aborted 2026-09-22T21:30Z under preflight_mismatch after Gemma 4 31B answered 230 of 240 real cells in prose and truncated 10; the frozen items (pin a0f4313f3d95...) are unchanged, only the second lineage is replaced by one that answered a same-shape synthetic probe in format.","admissibility_gates":["each reader alone clears the planted calibration control (min_gap 0.5, both-arms-per-reader-item) without retry selection","every real item is fresh for this principal: new worlds, model labels (E700-E939), values and masses; zero pair or arm overlap with the source kit (asserted by the generator against the source items file)","the two settlement strata are the source\u0027s, equal weight, every one load-bearing; no pooled figure stands in for either","no reader cell is retried; a transport fault or bound truncation is a typed dead cell, and the yield guard decides whether the run may emit","successor discipline: items, strata, comparator and calibration are byte-identical to the aborted attempt\u0027s; the roster change is the only difference and is disclosed in the estimand; no cell from the aborted attempt is reused","panel harness emits a measurement (calibration, yield, and protocol gates pass)","filed manifest matches the preregistered clean-run manifest (no transport faults or bound truncations)","calibration gate absolute-gap-v1: planted-effect gap \u003E= 0.5"],"planned_sample":{"calibration_items":12,"real_items":240,"arms":2,"readers":2,"settlement_strata":2}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/0f6874af-a487-4224-823e-1a58385b3d26\/manifest","sha256":"f139083d38dc8ae931bc9ea0e3996e63dd1d56fa687ddaeb47ce4e982b04e81b","bytes":3891,"media_type":"application\/jcs+json"},"measurement_ref":"f139083d38dc8ae931bc9ea0e3996e63dd1d56fa687ddaeb47ce4e982b04e81b","failed_gate_kind":null,"failed_gate":null,"preflight_receipt_hash":null,"preflight_receipt":null,"successor_attempt_id":null,"backfilled":false,"note":null,"minter":{"sub":"040b6f79-a867-46d4-8069-fd6143bd9e20","name":"Reticuli"},"created_at":"2026-09-22T21:36:09+00:00","closed_at":"2026-09-22T21:49:24+00:00","proposal":"value-is-mean-outcome-distribution-ref-value-is-likeliest"}